| Radeon | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Model: | 2000–02: Radeon 7000, 8000, 9000 series | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Model1: | 2004–05: Radeon X300-X600, X700, X800, X1000 series | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Model2: | 2007–13: Radeon HD 2000, HD 3000, HD 4000, HD 5000, HD 6000, HD 7000, HD 8000 series | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Model3: | 2013–present: Radeon R5/R7/R9 200, R5/R7/R9 300, RX 400, RX 500, RX Vega, RX 5000, RX 6000, RX 7000 series | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Created: | by ATI Technologies | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Transistors: |
| |||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Predecessor: | Rage | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Process: | 180 nm to 5 nm | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Designfirm: | ATI (2000–2006) AMD (2006–present) | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Manufacturer: | ATI Technologies AMD Samsung TSMC | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Radeon is a brand of computer products, including graphics processing units, random-access memory, RAM disk software, and solid-state drives, produced by Radeon Technologies Group, a division of AMD.[1] The brand was launched in 2000 by ATI Technologies, which was acquired by AMD in 2006 for US$5.4 billion.
Radeon Graphics is the successor to the Rage line. Four different families of microarchitectures can be roughly distinguished, the fixed-pipeline family, the unified shader model-families of TeraScale, Graphics Core Next, and RDNA. ATI/AMD have developed different technologies, such as TruForm, HyperMemory, HyperZ, XGP, Eyefinity for multi-monitor setups, PowerPlay for power-saving, CrossFire (for multi-GPU) or Hybrid Graphics. A range of SIP blocks is also to be found on certain models in the Radeon products line: Unified Video Decoder, Video Coding Engine and TrueAudio.
The brand was previously only known as "ATI Radeon" until August 2010, when it was renamed to increase AMD's brand awareness on a global scale.[2] Products up to and including the HD 5000 series are branded as ATI Radeon, while the HD 6000 series and beyond use the new AMD Radeon branding.[3]
On 11 September 2015, AMD's GPU business was split into a separate unit known as Radeon Technologies Group, with Raja Koduri as Senior Vice President and chief architect.[1] [4]
AMD does not distribute Radeon cards directly to consumers (though some exceptions can be found).[5] Instead, it sells Radeon GPUs to third-party manufacturers, who build and sell the Radeon-based video cards to the OEM and retail channels. Manufacturers of the Radeon cards—some of whom also make motherboards—include ASRock, Asus, Biostar, Club 3D, Diamond, Force3D, Gainward, Gigabyte, HIS, MSI, PowerColor, Sapphire, VisionTek, and XFX.
Early generations were identified with a number and major/minor alphabetic prefix. Later generations were assigned code names. New or heavily redesigned architectures have a prefix of R (e.g., R300 or R600) while slight modifications are indicated by the RV prefix (e.g., RV370 or RV635).
The first derivative architecture, RV200, did not follow the scheme used by later parts.
See main article: Radeon R100 series.
The Radeon, first introduced in 2000, was ATI's first graphics processor to be fully DirectX 7 compliant. R100 brought with it large gains in bandwidth and fill-rate efficiency through the new HyperZ technology.
The RV200 was a die-shrink of the former R100 with some core logic tweaks for clockspeed, introduced in 2002. The only release in this generation was the Radeon 7500, which introduced little in the way of new features but offered substantial performance improvements over its predecessors.
See main article: Radeon R200 series.
ATI's second generation Radeon included a sophisticated pixel shader architecture. This chipset implemented Microsoft's pixel shader 1.4 specification for the first time.
Its performance relative to competitors was widely perceived as weak, and subsequent revisions of this generation were cancelled in order to focus on development of the next generation.
See main article: Radeon R300 series. The R300 was the first GPU to fully support Microsoft's DirectX 9.0 technology upon its release in 2001. It incorporated fully programmable pixel and vertex shaders.
About a year later, the architecture was revised to allow for higher frequencies, more efficient memory access, and several other improvements in the R350 family. A budget line of RV350 products was based on this refreshed design with some elements disabled or removed.
Models using the new PCI Express interface were introduced in 2004. Using 110-nm and 130-nm manufacturing technologies under the X300 and X600 names, respectively, the RV370 and RV380 graphics processors were used extensively by consumer PC manufacturers.
While heavily based upon the previous generation, this line included extensions to the Shader Model 2 feature-set. Shader Model 2b, the specification ATI and Microsoft defined with this generation, offered somewhat more shader program flexibility.
ATI's DirectX 9.0c series of graphics cards, with complete shader Model 3.0 support. Launched in October 2005, this series brought a number of enhancements including the floating point render target technology necessary for HDR rendering with anti-aliasing.
See main article: TeraScale (microarchitecture).
See main article: Radeon HD 2000 series and Radeon HD 3000 series. ATI's first series of GPUs to replace the old fixed-pipeline and implement unified shader model. Subsequent revisions tuned the design for higher performance and energy efficiency, resulting in the ATI Mobility Radeon HD series for mobile computers.
See main article: Radeon HD 4000 series. Based on the R600 architecture. Mostly a bolstered with many more stream processors, with improvements to power consumption and GDDR5 support for the high-end RV770 and RV740(HD4770) chips. It arrived in late June 2008. The HD 4850 and HD 4870 have 800 stream processors and GDDR3 and GDDR5 memory, respectively. The 4890 was a refresh of 4870 with the same amount of stream processors yet higher clock rates due to refinements. The 4870x2 has 1600 stream processors and GDDR5 memory on an effective 512-bit memory bus with 230.4 Gbit/s video memory bandwidth available.
See main article: Radeon HD 5000 series. The series was launched on 23 September 2009. It featured a 40 nm fabrication process for the entire product line (only the HD4770 (RV740) was built on this process previously), with more stream cores and compatibility with the next major version of the DirectX API, DirectX 11, which launched on 22 October 2009 along with Microsoft Windows 7. The Rxxx/RVxxx codename scheme was scrapped entirely. The initial launch consisted of only the 5870 and 5850 models. ATI released beta drivers that introduced full OpenGL 4.0 support on all variants of this series in March 2010.[6]
See main article: Radeon HD 6000 series. This is the first series to be marketed solely under the "AMD" brand. It features a 3rd generation 40 nm design, rebalancing the existing architecture with redesigned shaders to give it better performance. It was released first on 22 October 2010, in the form of the 6850 and 6870. 3D output is enabled with HDMI 1.4a and DisplayPort 1.2 outputs.
See main article: Graphics Core Next.
See main article: Radeon HD 7000 series. "Southern Islands" was the first series to feature the new compute microarchitecture known as "Graphics Core Next"(GCN). GCN was used among the higher end cards, while the VLIW5 architecture utilized in the previous generation was used in the lower end, OEM products. However, the Radeon HD 7790 uses GCN 2, and was the first product in the series to be released by AMD on 9 January 2012.
See main article: Radeon HD 8000 series. The "Sea Islands" were OEM rebadges of the 7000 series, with only three products, code named Oland, available for general retail. The series, just like the "Southern Islands", used a mixture of VLIW5 models and GCN models for its desktop products.
See main article: Radeon 200 series. "Volcanic Islands" GPUs were introduced with the AMD Radeon Rx 200 series, and were first released in late 2013.[7] The Radeon Rx 200 line is mainly based on AMD's GCN architecture, with the lower end, OEM cards still using VLIW5. The majority of desktop products use GCN 1, while the R9 290x/290 & R7 260X/260 use GCN 2, and with only the R9 285 using the new GCN 3.[8]
See main article: Radeon 300 series. GPUs codenamed "Caribbean Islands"[9] were introduced with the AMD Radeon Rx 300 series, released in 2015. This series was the first to solely use GCN based models, ranging from GCN 1st to GCN 3rd Gen, including the GCN 3-based Fiji-architecture models named Fury X, Fury, Nano and the Radeon Pro Duo.
See main article: Radeon 400 series and Radeon 500 series. GPUs codenamed "Arctic Islands" were first introduced with the Radeon RX 400 series in June 2016 with the announcement of the RX 480.[10] These cards were the first to use the new Polaris chips which implements GCN 4th Gen on the 14 nm fab process. The RX 500 series released in April 2017 also uses Polaris chips.[11]
See main article: Radeon RX Vega series.
See main article: RDNA (microarchitecture).
See main article: Radeon RX 5000 series. On 27 May 2019, at COMPUTEX 2019, AMD announced the new 'RDNA' graphics micro-architecture,[12] which is to succeed the Graphics Core Next micro-architecture. This is the basis for the Radeon RX 5700-series graphics cards, the first to be built under the codename 'Navi'. These cards feature GDDR6 SGRAM and support for PCI Express 4.0.
See main article: Radeon RX 6000 series. On 5 March 2020, AMD publicly announced its plan to release a "refresh" of the RDNA micro-architecture.[13] Dubbed as the RDNA 2 architecture, it was stated to succeed the first-gen RDNA micro-architecture and was initially scheduled for a release in Q4 2020. RDNA 2 was confirmed as the graphics microarchitecture featured in the Xbox Series X and Series S consoles[14] from Microsoft, and PlayStation 5[15] from Sony, with proprietary tweaks and different GPU configurations in each systems' implementation.
AMD unveiled the Radeon RX 6000 series, its next-gen RDNA 2 graphics cards at an online event on 28 October 2020.[16] [17] The lineup consists of the RX 6800, RX 6800 XT and RX 6900 XT.[18] [19] The RX 6800 and 6800 XT launched on 18 November 2020, with the RX 6900 XT being released on 8 December 2020.[20] Further variants including a Radeon RX 6700 (XT) series based on Navi 22, launched on 18 March 2021, a Radeon RX 6600(XT) series based on Navi 23, launched on 11 August 2021 (that is the 6600XT release date, the RX 6600 launched on 13 October 2021), and a Radeon RX 6500(XT), launched on 19 January 2022.[21] [22] [23] [24] [25]
See also: ROCm and GPUOpen. Some generations vary from their predecessors predominantly due to architectural improvements, while others were adapted primarily to new manufacturing processes with fewer functional changes. The table below summarizes the APIs supported in each Radeon generation (including pre-Radeon ATI GPUs). Also see AMD FireStream and AMD FirePro branded products.
See main article: AMD Radeon Software.
On 24 November 2015, AMD released a new version of their graphics driver following the formation of the Radeon Technologies Group (RTG) to provide extensive software support for their graphics cards. This driver, labelled Radeon Software Crimson Edition, overhauls the UI with Qt, resulting in better responsiveness from a design and system perspective. It includes a new interface featuring a game manager, clocking tools, and sections for different technologies.[26]
Unofficial modifications such as Omega drivers and DNA drivers were available. These drivers typically consist of mixtures of various driver file versions with some registry variables altered and are advertised as offering superior performance or image quality. They are, of course, unsupported, and as such, are not guaranteed to function correctly. Some of them also provide modified system files for hardware enthusiasts to run specific graphics cards outside of their specifications.
Radeon Software is being developed for Microsoft Windows and Linux., other operating systems are not officially supported. This may be different for the Radeon Pro brand, which is based on identical hardware but features OpenGL-certified graphics device drivers.
ATI previously offered driver updates for their retail and integrated Macintosh video cards and chipsets. ATI stopped support for Mac OS 9 after the Radeon R200 cards, making the last officially supported card the Radeon 9250. The Radeon R100 cards up to the Radeon 7200 can still be used with even older classic Mac OS versions such as System 7, although not all features are taken advantage of by the older operating system.[27]
Ever since ATI's acquisition by AMD, ATI no longer supplies or supports drivers for classic Mac OS nor macOS. macOS drivers can be downloaded from Apple's support website, while classic Mac OS drivers can be obtained from 3rd party websites that host the older drivers for users to download. ATI used to provide a preference panel for use in macOS called ATI Displays which can be used both with retail and OEM versions of its cards. Though it gives more control over advanced features of the graphics chipset, ATI Displays has limited functionality compared to Catalyst for Windows or Linux.
The free and open-source for Direct Rendering Infrastructure has been under constant development by the Linux kernel developers, by 3rd party programming enthusiasts and by AMD employees. It is composed out of five parts:
The free and open-source driver supports many of the features available in Radeon-branded cards and APUs, such as multi-monitor or hybrid graphics.
The free and open-source drivers are primarily developed on Linux and for Linux.
Being entirely free and open-source software, the free and open-source drivers can be ported to any existing operating system. Whether they have been, and to what extent depends entirely on the man-power available. Available support shall be referenced here.
FreeBSD adopted DRI, and since Mesa 3D is not programmed for Linux, it should have identical support.
MorphOS supports 2D and 3D acceleration for Radeon R100, R200 and R300 chipsets.[30]
AmigaOS 4 supports Radeon R100, R200, R300,[31] R520 (X1000 series), R700 (HD 4000 series), HD 5000 (Evergreen) series, HD 6000 (Northern Islands) series and HD 7000 (Southern Islands) series.[32] The RadeonHD AmigaOS 4 driver has been developed by Hans de Ruiter[33] funded and owned by A-EON Technology Ltd. The older R100 and R200 "ATIRadeon" driver for AmigaOS, originally developed Forefront Technologies has been acquired by A-EON Technology Ltd in 2015.
In the past ATI provided hardware and technical documentation to the Haiku Project to produce drivers with full 2D and video in/out support on older Radeon chipsets (up to R500) for Haiku. A new Radeon HD driver was developed with the unofficial and indirect guidance of AMD open source engineers and currently exists in recent Haiku versions. The new Radeon HD driver supports native mode setting on R600 through Southern Islands GPU's.[34]
AMD (and its predecessor ATI) have released a series of embedded GPUs targeted toward medical, entertainment, and display devices.
| Model | Released | Shaders (Compute Units) | FP power Single Precision | Memory | Memory band-with | Memory clock | OpenGL Version | OpenCL Version | DirectX Version | Vulkan | UVD | Power | Output | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| E9550 (Polaris, GCN 4)[35] | 2016-09-27 | 2304 (36 CU) | 5834 GFLOPS | 8 GB GDDR5 | 256 Bit | 2000 MHz | 4.5 | 2.0 | 12 | 1.1 | 6.3 | 95 Watt | MXM-B | |
| E9260 (GCN 4)[36] | 2016-09-27 | 896 (14 CU) | 2150 GFLOPS | 4 GB GDDR5 | 128 Bit | 1750 MHz | 4.5 | 2.0 | 12 | 1.1 | 6.3 | 50 W | PCIe 3.0, MXM-A | |
| E9171 MCM (GCN 4)[37] | 2017-10-03 | 512 (8 CU) | 1248 GFLOPS | 4 GB GDDR5 | 128 Bit | 1500 MHz | 4.5 | 2.0 | 12 | 1.1 | 6.3 | 40 W | PCIe 3.0 x8 | |
| E9172 MXM (GCN 4)[38] | 2017-10-03 | 512 (8 CU) | 1248 GFLOPS | 2 GB GDDR5 | 64 Bit | 1500 MHz | 4.5 | 2.0 | 12 | 1.1 | 6.3 | 35 W | MXM-A 3.0 | |
| E9173 PCIe (GCN 4)[39] | 2017-10-03 | 512 (8 CU) | 1248 GFLOPS | 2 GB GDDR5 | 64 Bit | 1500 MHz | 4.5 | 2.0 | 12 | 1.1 | 6.3 | 35 W | PCIe 3.0 x8 | |
| E9174 MXM (GCN 4)[40] | 2017-10-03 | 512 (8 CU) | 1248 GFLOPS | 4 GB GDDR5 | 128 Bit | 1500 MHz | 4.5 | 2.0 | 12 | 1.1 | 6.3 | 50 W | MXM-A 3.0 | |
| E9175 PCIe (GCN 4)[41] | 2017-10-03 | 512 (8 CU) | 1248 GFLOPS | 4 GB GDDR5 | 128 Bit | 1500 MHz | 4.5 | 2.0 | 12 | 1.1 | 6.3 | 50 W | PCIe 3.0 x8 | |
| E8950 (GCN 3)[42] | 2015-09-29 | 2048 (32 CU) | 3010 GFLOPS | 8 GB GDDR5 | 128 Bit | 1500 MHz | 4.5 | 2.0 | 12 | 1.1 | 4.2 | 95 W | MXM-B | |
| E8870 (GCN 2)[43] | 2015-09-29 | 768 (12 CU) | 1536 GFLOPS | 4 GB GDDR5 | 128 Bit | 1500 MHz | 4.5 | 2.0 | 12 | 1.1 | 4.2 | 75 W | PCIe 3.0, MXM-B | |
| E8860 (GCN 1)[44] [45] [46] | 2014-01-25 | 640 (10 CU) | 800 GFLOPS | 2 GB GDDR5 | 128 Bit | 1125 MHz | 4.5 | 1.2 | 12.0 | 1.0 | 3.1 | 37 W | PCIe 3.0, MXM-B | |
| E6760 (Turks)[47] [48] | 2011-05-02 | 480 (6 CU) | 576 GFLOPS | 1 GB GDDR5 | 128 Bit | 800 MHz | 4.3 | 1.2 | 11 | N/A | 3.0 | 35 W | PCIe 2.1, MXM-A, MCM | |
| E6465 (Caicos)[49] [50] | 2015-09-29 | 160 (2 CU) | 192 GFLOPS | 2 GB GDDR5 | 64 Bit | 800 MHz | 4.5 | 1.2 | 11.1 | N/A | 3.0 | < 20 W | PCIe 2.1, MXM-A, MCM | |
| E6460 (Caicos)[51] [52] | 2011-04-07 | 160 (2 CU) | 192 GFLOPS | 512 MB GDDR5 | 64 Bit | 800 MHz | 4.5 | 1.2 | 11.1 | N/A | 3.0 | 16 W | PCIe 2.1, MXM-A, MCM | |
| E4690 (RV730)[53] | 2009-06-01 | 320 (4 CU) | 388 GFLOPS | 512 MB GDDR3 | 128 Bit | 700 MHz | 3.3 | 1.0 | 10.1 | N/A | 2.2 | 30 W | MXM-II | |
| E2400 (RV610)[54] | 2006-07-28 | 40 (2 CU) | 48 GFLOPS | 128 MB GDDR3 | 64 Bit | 700 MHz | 3.3 | ATI Stream | 10.0 | N/A | 1.0 | 25 W | MXM-II |
In August 2011, AMD expanded the Radeon name to include random access memory modules under the AMD Memory line. The initial releases included 3 types of 2GiB DDR3 SDRAM modules: Entertainment (1333 MHz, CL9 9-9), UltraPro Gaming (1600 MHz, CL11 11-11) and Enterprise (specs to be determined).[55]
On May 8, 2013, AMD announced the release of Radeon RG2133 Gamer Series Memory.[56]
Radeon R9 2400 Gamer Series Memory was released on January 16, 2014.[57] [58]
Dataram Corporation is manufacturing RAM for AMD.[59]
On September 6, 2012, Dataram Corporation announced it has entered into a formal agreement with AMD to develop an AMD-branded version of Dataram's RAMDisk software under the name Radeon RAMDisk, targeting gaming enthusiasts seeking exponential improvements in game load times leading to an enhanced gaming experience.[60] The freeware version of Radeon RAMDisk software supports Windows Vista and later with minimum 4GiB memory, and supports maximum of 4GiB RAM disk[61] (6GiB if AMD Radeon Value, Entertainment, Performance Edition or Products installed, and Radeon RAMDisk is activated between 2012-10-10 and 2013-10-10[62]). Retail version supports RAM disk size between 5MiB to 64GiB.[63] [64]
Version 4.1 was released in May 8, 2013.[56]
In 2014-04-02, Dataram Corporation announced it has signed an Agreement with Elysium Europe Ltd. to expand sales penetration in Europe, the Middle East and Africa. Under this Agreement, Elysium is authorized to sell AMD Radeon RAMDisk software. Elysium is focusing on etailers, retailers, system builders and distributors.[65]
AMD planned to enter solid state drive market with the introduction of R7 models powered by Indilinx Barefoot 3 controller and Toshiba 19 nm MLC flash memory, and initially available in 120G, 240G, 480G capacities.[66] [67] The R7 Series SSD was released on August 9, 2014, which included Toshiba's A19 MLC NAND flash memory, Indilinx Barefoot 3 M00 controller.[68] These components are the same as in the SSD OCZ Vector 150 model.